Please wait a minute...
Advanced Search
数据分析与知识发现  2018, Vol. 2 Issue (2): 74-85     https://doi.org/10.11925/infotech.2096-3467.2017.0886
  研究论文 本期目录 | 过刊浏览 | 高级检索 |
基于用户浏览行为的兴趣识别管理模型*
刘洪伟1, 高鸿铭1, 陈丽2(), 詹明君1, 梁周扬1
1(广东工业大学管理学院 广州 510520)
2(广东青年职业学院 广州 510507)
Identifying User Interests Based on Browsing Behaviors
Liu Hongwei1, Gao Hongming1, Chen Li2(), Zhan Mingjun1, Liang Zhouyang1
1(School of Management, Guangdong University of Technology, Guangzhou 510520, China)
2(Guangdong Youth Vocational College, Guangzhou 510507, China)
全文: PDF (1432 KB)   HTML ( 5
输出: BibTeX | EndNote (RIS)      
摘要 

目的】了解用户在线购物中的兴趣需求变化有利于个性化推荐。本文提出结合用户浏览行为分析的隐式动态兴趣识别和管理模型。【方法】通过三阶段实验构造用户点击流数据, 以天猫和淘宝网页功能键为数据粒度对页面分类, 再采用Bisecting K-means聚类算法进行兴趣状态挖掘, 最后总结归纳兴趣与行为的特征映射。【结果】用户隐式兴趣存在4种状态: 关注、理解信息、态度和购买意图, 在态度和购买意图状态下, 更倾向于产生购买; 在不同状态的浏览路径特征有所差异。【局限】未添加网页广告促销等非结构化数据进行分析。【结论】从实时动态兴趣的角度, 对购物决策中兴趣的状态进行验证挖掘, 拓展动态兴趣研究; 为电商网站管理用户行为提供了一个实现动态个性化推荐的视角。

服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
刘洪伟
高鸿铭
陈丽
詹明君
梁周扬
关键词 隐式兴趣点击流Bisecting K-means算法    
Abstract

[Objective] This paper proposes a model to identify the interests of online shoppers based on their browsing behaviors, aiming to improve the personalized recommendation services. [Methods] First, we launched experiment to collect clickstream data from Taobao and TMall. Second, we used the Bisecting K-means algorithm to analyze the retrieved data. Finally, we established the relationship mapping structure between interests and behaviors. [Results] We found four types of user’s implicit interests: Attention, Comprehension, Attitudes and Intention. Users with the Attitude and Intention types tended to make purchase. The characteristics of browsing paths were different among the users. [Limitations] We did not examine unstructured data, i.e., online sales advertisements, in this study. [Conclusions] This paper investigates the user interests in online shopping, and then improve the personalized recommendation services of the E-commerce platforms.

Key wordsImplicit Interest    Clickstream    Bisecting K-means Algorithm
收稿日期: 2017-09-01      出版日期: 2018-03-07
ZTFLH:  TP391.4 F713.8  
基金资助:*本文系国家自然科学基金资助项目“电子商务交互式决策助手对用户购物决策行为的影响与演化研究”(项目编号: 71671048)和广东工业大学研究生创新项目“基于双元创新活动的顾客参与对口碑推荐的影响研究”(项目编号: 2017YJSCX034)的研究成果之一
引用本文:   
刘洪伟, 高鸿铭, 陈丽, 詹明君, 梁周扬. 基于用户浏览行为的兴趣识别管理模型*[J]. 数据分析与知识发现, 2018, 2(2): 74-85.
Liu Hongwei,Gao Hongming,Chen Li,Zhan Mingjun,Liang Zhouyang. Identifying User Interests Based on Browsing Behaviors. Data Analysis and Knowledge Discovery, 2018, 2(2): 74-85.
链接本文:  
https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.2096-3467.2017.0886      或      https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/Y2018/V2/I2/74
  本文研究框架
字段 含义
user_Id 用户ID
sessionId 会话ID
tabId 标签页记录ID
title 网页主题
url 用户访问地址
visitedTime 用户访问时间
goodlist 商品列表
Info 鼠标点击信息
  浏览器日志字段及含义
  三阶段实验设计框架
缩写 H A S D F G R B P Y V T C O
类名 主页 账户 付款
购买
加入购物车&
收藏夹
购物车 商品 评价 品牌或旗舰店 价格 人气 销量 商品
属性
目录 其他
频数 138 96 7 30 52 170 11 142 17 5 4 588 438 74
频率(%) 7.79 5.42 0.40 1.69 2.93 9.59 0.62 8.01 0.96 0.28 0.23 33.18 24.72 4.18
  页面类别统计描述表
变量 均值 标准差 最小值 中位数 最大值
页面持续时间(秒) 12.28 45.32 0.00 3.00 1492.00
页面相对浏览
时间率(%)
0.71 3.42 0.00 0.09 100.00
页面点击率(%) 27.67 18.76 0.27 26.01 100.00
会话访问深度(页) 28.20 25.72 2.00 22.00 102.00
  兴趣指标描述性统计
  轮廓系数与K的关系
动态兴趣 Time Timeratio Clickratio Sessiondepth
第1簇 5.283270 0.5805210 50.57808 16.92205
第2簇 7.042510 0.2328121 19.05581 64.23077
第3簇 11.558824 0.6666170 17.15118 12.02801
第4簇 155.5405 8.1338870 21.005 19.62162
  4类用户兴趣的簇中心
  不同兴趣状态的数据分布可视化
4类动态兴趣 相关系数
第1簇 /
第2簇 -0.022
第3簇 -0.081
第4簇 0.679**
  各簇中使用购物车行为次数与实际购买次数相关检验
  不同兴趣状态的D类页面频数均值估计碎石图
  某会话中的用户部分兴趣状态-浏览路径图
  不同状态下的一步转移概率可视化表示
[1] 戴德宝, 刘西洋, 范体军. “互联网+”时代网络个性化推荐采纳意愿影响因素研究[J]. 中国软科学, 2015(8): 163-172.
[1] (Dai Debao, Liu Xiyang, Fan Tijun.Research on the Adoption Intention of Online Personalized Recommender in the Internet Plus Era[J]. China Soft Science, 2015(8): 163-172.)
[2] Ding A W, Li S, Chatterjee P.Learning User Real-Time Intent for Optimal Dynamic Web Page Transformation[J]. Information Systems Research, 2015, 26(2): 339-359.
doi: 10.1287/isre.2015.0568
[3] Rana C, Jain S K.A Study of the Dynamic Features of Recommender Systems[J]. Artificial Intelligence Review, 2015, 43(1): 141-153.
doi: 10.1007/s10462-012-9359-6
[4] Mladenic D.Text-Learning and Related Intelligent Agents: A Survey[J]. IEEE Intelligent Systems & Their Applications, 2002, 14(4): 44-54.
doi: 10.1109/5254.784084
[5] Chu W, Park S T.Personalized Recommendation on Dynamic Content Using Predictive Bilinear Models[C]//Procedings of the 18th International Conference on World Wide Web, Madrid, Spain. New York, NY, USA: ACM, 2009: 691-700.
[6] Burke R.Hybrid Web Recommender Systems [A]// The Adaptive Web: Methods and Strategies of Web Personalization, Lecture Notes in Computer Science[M]. Springer, 2007: 377-408.
[7] Kardan A A, Ebrahimi M.A Novel Approach to Hybrid Recommendation Systems Based on Association Rules Mining for Content Recommendation in Asynchronous Discussion Groups[J]. Information Sciences, 2013, 219: 93-110.
doi: 10.1016/j.ins.2012.07.011
[8] Li C, Jiang Z.A Hybrid News Recommendation Algorithm Based on User’s Browsing Path[C]// Procedings of the IEEE/ACIS International Conference on Computer and Information Science, Okayama, Japan. IEEE, 2016: 1-4.
[9] 张奇. 天猫推荐算法实践 [EB/OL]. (2014-06-22). [2017- 07-10]. .
[9] (Zhang Qi. Recommendation of TMall [EB/OL]. (2014-06-22). [2017-07-10].
[10] Shang M S, Chen G X, Dai S X, et al.Interest-Driven Model for Human Dynamics[J]. Chinese Physics Letters, 2010, 27(4): 48701-48703.
doi: 10.1088/0256-307X/27/4/048701
[11] Barabási A L.The Origin of Bursts and Heavy Tails in Human Dynamics[J]. Nature, 2005, 435(7039): 207-211.
doi: 10.1038/nature03459 pmid: 15889093
[12] Zhao Z D, Yang Z, Zhang Z, et al. Emergence of Scaling in Human-Interest Dynamics [J]. Scientific Reports, 2013, 3(12). Article No.: 3472
doi: 10.1038/srep03472 pmid: 3858797
[13] Han X P, Zhou T, Wang B H.Modeling Human Dynamics with Adaptive Interest[J]. New Journal of Physics, 2007, 10(7): 1983-1989.
doi: 10.1088/1367-2630/10/7/073010
[14] Estrin D. Small Data, Where n = me[J]. Communications of the ACM, 2014, 57(4): 32-34.
[15] Zahoor S, Bedekar M, Kosamkar P K.User Implicit Interest Indicators Learned from the Browser on the Client Side[C]//Proceedings of International Conference on Information and Communication Technology for Competitive Strategies. ACM, 2014.
[16] Claypool M, Le P, Wased M, et al.Implicit Interest Indicators[C]//Proceedings of the 6th International Conference on Intelligent User Interfaces, New Mexico, USA. New York, NY, USA: ACM, 2000: 33-40.
[17] 崔春生. 基于隐式浏览输入的用户聚类分析[J]. 计算机应用研究, 2011, 28(8): 2862-2864.
doi: 10.3969/j.issn.1001-3695.2011.08.017
[17] (Cui Chunsheng.User Clustering Analysis Based on Implicit Navigation[J]. Application Research of Computers, 2011, 28(8): 2862-2864.)
doi: 10.3969/j.issn.1001-3695.2011.08.017
[18] Lieberman H.Letizia: An Agent That Assists Web Browsing[C]//Proceedings of the 14th International Joint Conference on Artificial Intelligence.1995, 1: 924-929.
[19] Kuo R J, Liao J L, Tu C.Integration of ART2 Neural Network and Genetic K-means Algorithm for Analyzing Web Browsing Paths in Electronic Commerce[J]. Decision Support Systems, 2005, 40(2): 355-374.
doi: 10.1016/j.dss.2004.04.010
[20] Jayawardhena C, Dennis C, Wright L T.Consumers Online: Intentions, Orientations and Segmentation[J]. International Journal of Retail & Distribution Management, 2007, 35(6): 515-526.
doi: 10.1108/09590550710750377
[21] 朱志国. 基于隐马尔可夫链模型的电子商务用户兴趣导航模式发现[J]. 中国管理科学, 2014, 22(4): 67-73.
[21] (Zhu Zhiguo.Discovery of E-Commerce Users’ Interest Navigation Patterns Based on Hidden Markov Chains Model[J].Chinese Journal of Management Science, 2014, 22(4): 67-73.)
[22] 付关友, 朱征宇. 个性化服务中基于行为分析的用户兴趣建模[J]. 计算机工程与科学, 2005, 27(12): 76-78.
doi: 10.3969/j.issn.1007-130X.2005.12.026
[22] (Fu Guanyou, Zhu Zhengyu.A User Interest Modele Based on the Analysis of User Behaviors for Personalization[J]. Computer Engineering & Science, 2005, 27(12): 76-78.)
doi: 10.3969/j.issn.1007-130X.2005.12.026
[23] Li B, Sun B, Montgomery A L.Cross-Selling the Right Product to the Right Customer at the Right Time[J]. Journal of Marketing Research, 2011, 48(4): 683-700.
doi: 10.2307/23033447
[24] Machleit K A, Allen C T, Madden T J.The Mature Brand and Brand Interest: An Alternative Consequence of Ad-Evoked Affect[J]. Journal of Marketing, 1993, 57(4): 72-82.
doi: 10.2307/1252220
[25] Duan W J, Gu B, Whinston A B.The Dynamics of Online Word-Of-Mouth and Product Sales — An Empirical Investigation of the Movie Industry[J]. Journal of Retailing, 2008, 84(2): 233-242.
doi: 10.1016/j.jretai.2008.04.005
[26] Moe W W.Buying, Searching, or Browsing: Differentiating Between Online Shoppers Using In-Store Navigational Clickstream[J]. Journal of Consumer Psychology, 2003, 13(1): 29-39.
doi: 10.1207/S15327663JCP13-1&2_03
[27] Montgomery A L, Li S, Srinivasan K, et al.Modeling Online Browsing and Path Analysis Using Clickstream Data[J]. Marketing Science, 2004, 23(4): 579-595.
doi: 10.1287/mksc.1040.0073
[28] Howard J A, Sheth J N.The Theory of Buyer Behavior[M]. New York: Wiley, 1969: 421-449.
[29] MacQueen J. Some Methods for Classification and Analysis of MultiVariate Observations[C]// Proceedings of the 5th Berkeley Symposium on Mathematical Statistics and Probability. 1967: 281-297.
[30] Ball G H, Hall D J.A Clustering Technique for Summarizing Multivariate Data[J]. Systems Research & Behavioral Science, 1967, 12(2): 153-155.
doi: 10.1002/bs.3830120210 pmid: 6030099
[31] Jain A K.Data Clustering: 50 Years Beyond K-means[J]. Pattern Recognition Letters, 2010, 31(8): 651-666.
doi: 10.1016/j.patrec.2009.09.011
[32] Steinley D.K-Means Clustering: A Half-Century Synthesis[J]. British Journal of Mathematical and Statistical Psychology, 2006, 59(1): 1-34.
doi: 10.1348/000711005X48266 pmid: 16709277
[33] Savaresi S M, Boley D L.On the Performance of Bisecting K-Means and PDDP[J]. Intelligent Data Analysis, 2004, 8(4): 345-362.
doi: 10.1137/1.9781611972719.5
[34] Rousseeuw P.Silhouettes: A Graphical Aid to the Interpretation and Validation of Cluster Analysis[J]. Journal of Computational & Applied Mathematics, 1987, 20: 53-65.
doi: 10.1016/0377-0427(87)90125-7
[35] Kodinariya T M, Makwana P R.Review on Determining Number of Cluster in K-means Clustering[J]. International Journal of Advance Research in Computer Science and Management Studies, 2013, 1(6): 90-95.
[36] Samadi M, Yaghoob-Nejadi A.A Survey of the Effect of Consumers’ Perceived Risk on Purchase Intention in e-Shopping[J]. Business Intelligence Journal, 2009, 2(2): 261-275.
doi: 10.4236/jssm.2015.81012
[37] Close A G, Kukar-Kinney M.Beyond Buying: Motivations Behind Consumers’ Online Shopping Cart Use[J]. Journal of Business Research, 2010, 63(9): 986-992.
doi: 10.1016/j.jbusres.2009.01.022
[38] 殷晨. 网络促销对消费者冲动性购买行为的影响研究 [D]. 济南: 山东大学, 2013.
[38] (Yin Chen.Research on the Influence of the Network Promtion on Consumers’ Impluse Buying Behavior[D]. Ji’nan: Shandong University, 2013.)
[39] Asiegbu I F, Powei D M, Iruka C H.Consumer Attitude: Some Reflections on Its Concept, Trilogy, Relationship with Consumer Behavior, and Marketing Implications[J]. European Journal of Business and Management, 2012, 4(13): 38-50.
[40] Hawkins D I, Mothersbaugh D L, Best R J.Consumer Behavior: Building Marketing Strategy[M]. McGraw-Hill Irwin, 2013.
[41] Fishbein M, Ajzen I. Belief, Attitude, Intention, and Behavior: An Introduction to Theory and Research[M]. Addison-Wesley Pub. Co., 1975.
[42] Bundesen C, Habekost T, Kyllingsbaek S.A Neural Theory of Visual Attention: Bridging Cognition and Neurophysiology[J]. Psychological Review, 2005, 112(2): 291-328.
doi: 10.1037/0033-295X.112.2.291
[43] Russo J E, Leclerc F.An Eye-Fixation Analysis of Choice Processes for Consumer Nondurables[J]. Journal of Consumer Research, 1994, 21(2): 274-290.
doi: 10.1086/209397
[44] Clement J.Visual Influence on In-store Buying Decisions: An Eye-Track Experiment on the Visual Influence of Packaging Design[J]. Journal of Marketing Management, 2007, 23(9-10): 917-928.
doi: 10.1362/026725707X250395
[45] Glaholt M G, Reingold E M.Eye Movement Monitoring as a Process Tracing Methodology in Decision Making Research[J]. Journal of Neuroscience, Psychology, and Economics, 2011, 4(2): 125-146.
doi: 10.1037/a0020692
[46] Glöckner A, Herbold A K.An Eye‐Tracking Study on Information Processing in Risky Decisions: Evidence for Compensatory Strategies Based on Automatic Processes[J]. Journal of Behavioral Decision Making, 2011, 24(1): 71-98.
doi: 10.1002/bdm.684
[1] 易明,杨斌. 站点结构优化方法研究综述*[J]. 现代图书情报技术, 2008, 24(7): 61-65.
[2] 易明 . 基于全信息的站点页面预取研究[J]. 现代图书情报技术, 2006, 1(7): 47-51.
[3] 易明,饶洋辉 . 基于点击流数据的用户近期兴趣视图生成方法[J]. 现代图书情报技术, 2006, 1(6): 55-58.
[4] 易明,邓卫华,曹高辉 . 基于"点击流"数据的站点信息服务组织优化[J]. 现代图书情报技术, 2006, 22(1): 51-54.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 2015 《数据分析与知识发现》编辑部
地址:北京市海淀区中关村北四环西路33号 邮编:100190
电话/传真:(010)82626611-6626,82624938
E-mail:jishu@mail.las.ac.cn